Ornith-1.5: Self-Improving Open-Source MoE Models Rival Claude Opus

aftahi_ai · x · 2026-08-19

Ornith-1.5 is a family of open-source LLMs (9B Dense, 35B MoE, 397B MoE) released under the MIT license. It trains via end-to-end self-improvement strategies, enabling the model to propose tasks, generate scaffolds, and use experiences for reinforcement learning.

It achieves state-of-the-art performance among comparable open-source models:

Its performance in reasoning, agentic, and coding tasks is claimed to be comparable to Claude Opus 4.8.

Related event: Open-Source Ornith-1.5 Family Released, 397B MoE Claims Claude Opus-Level Performance(13 posts)→

Original post →

More from coding & agent

coding & agent channel →